llama2_7b_instruct_sft_dpo / train_results.json
yuansui's picture
Model save
e5879d7 verified
raw
history blame contribute delete
200 Bytes
{
"epoch": 7.272,
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 5.7891,
"train_samples": 100,
"train_samples_per_second": 138.19,
"train_steps_per_second": 1.382
}